| { |
| "best_metric": 0.06065525859594345, |
| "best_model_checkpoint": "saves/psy-course-info-chain/Ministral-8B-Instruct-2410/train/fold1/checkpoint-70", |
| "epoch": 4.938271604938271, |
| "eval_steps": 10, |
| "global_step": 125, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03950617283950617, |
| "grad_norm": 1.6908252239227295, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.5271, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 1.4812554121017456, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.5089, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 1.7392562627792358, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.4944, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 1.5803614854812622, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.5041, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 1.5030882358551025, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.5046, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 1.2708423137664795, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.4464, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 0.9933308362960815, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.3709, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 1.0247366428375244, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.3411, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 0.8926035761833191, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.2253, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.3223307132720947, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.2392, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.18373644351959229, |
| "eval_runtime": 21.8646, |
| "eval_samples_per_second": 2.058, |
| "eval_steps_per_second": 2.058, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.2646924257278442, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.131, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.7477754950523376, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.1715, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.7597765922546387, |
| "learning_rate": 0.0001, |
| "loss": 0.186, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.6708258390426636, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.127, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.6358998417854309, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.1325, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.7045351266860962, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.1638, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.5236542820930481, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.134, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.5597946047782898, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1074, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.4602213203907013, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.1043, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.36896851658821106, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.0713, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.0861930176615715, |
| "eval_runtime": 21.7187, |
| "eval_samples_per_second": 2.072, |
| "eval_steps_per_second": 2.072, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.7383498549461365, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1193, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.3550701141357422, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.0648, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.38411107659339905, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.0587, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.45563438534736633, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.0878, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.49741560220718384, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1095, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.40558576583862305, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.0843, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.3873986601829529, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.0755, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.5111972093582153, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.1168, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.3763158321380615, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.065, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.45760226249694824, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.0829, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.0754161924123764, |
| "eval_runtime": 21.7277, |
| "eval_samples_per_second": 2.071, |
| "eval_steps_per_second": 2.071, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.5380536913871765, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.0537, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.49315115809440613, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.0769, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.5270469188690186, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.1014, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.38571858406066895, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.0645, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.39681366086006165, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.0635, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.5890967845916748, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.0795, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.4773964583873749, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.0674, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.4928514063358307, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.0735, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.445029616355896, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.0742, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.41080373525619507, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0617, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.06417860090732574, |
| "eval_runtime": 21.7241, |
| "eval_samples_per_second": 2.071, |
| "eval_steps_per_second": 2.071, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.6075394153594971, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0787, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.2814483642578125, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.041, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.5756314992904663, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.0852, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.4882969260215759, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.0684, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.7817419171333313, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.0919, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.4328422248363495, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0744, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.6814473271369934, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.0377, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.4841972291469574, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.0573, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.6272240877151489, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.1251, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.3540237843990326, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.049, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.06583306193351746, |
| "eval_runtime": 21.7329, |
| "eval_samples_per_second": 2.071, |
| "eval_steps_per_second": 2.071, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.40502095222473145, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.057, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.3536899983882904, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0476, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.31685128808021545, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0481, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.544730544090271, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0911, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.3866436183452606, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0636, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.33278557658195496, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.032, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.3350634276866913, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.0373, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.35577404499053955, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.039, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.31525370478630066, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.0378, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.24784615635871887, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.031, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.062084294855594635, |
| "eval_runtime": 21.7224, |
| "eval_samples_per_second": 2.072, |
| "eval_steps_per_second": 2.072, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.4334273040294647, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.04, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.3710649907588959, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0576, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.5316567420959473, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0577, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.5347827672958374, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0575, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.38777875900268555, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0447, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.3923545777797699, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0356, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.3656608462333679, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.035, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.44439801573753357, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0539, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.4194432497024536, |
| "learning_rate": 5e-05, |
| "loss": 0.041, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.43789416551589966, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0492, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.06065525859594345, |
| "eval_runtime": 21.7293, |
| "eval_samples_per_second": 2.071, |
| "eval_steps_per_second": 2.071, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.5057860612869263, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0561, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.5790203809738159, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0716, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.6126314997673035, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0736, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.36969804763793945, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0526, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.47390681505203247, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.0521, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.4209699034690857, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.0536, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.39266717433929443, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0329, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.3905760645866394, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0364, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.36712077260017395, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0358, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.29166993498802185, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0197, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.062390394508838654, |
| "eval_runtime": 21.7255, |
| "eval_samples_per_second": 2.071, |
| "eval_steps_per_second": 2.071, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.3133505880832672, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0293, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.3561196029186249, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0358, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.34883326292037964, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0349, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.46272891759872437, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0522, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.32390132546424866, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0314, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.37340331077575684, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0324, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.5365275144577026, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0309, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.40333372354507446, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.024, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.3457601070404053, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0379, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.2961191236972809, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0252, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.06623963266611099, |
| "eval_runtime": 21.7492, |
| "eval_samples_per_second": 2.069, |
| "eval_steps_per_second": 2.069, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.6813238859176636, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.062, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.7956247329711914, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0467, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.48870277404785156, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0289, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.4606683552265167, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0364, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.5181449055671692, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.029, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.5148261785507202, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0328, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.37221795320510864, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0302, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.414410799741745, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0251, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.39491385221481323, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0329, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.5549201965332031, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0316, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.0674213320016861, |
| "eval_runtime": 21.75, |
| "eval_samples_per_second": 2.069, |
| "eval_steps_per_second": 2.069, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.7569711208343506, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0601, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.703424334526062, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0549, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.43300166726112366, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0212, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.4560510218143463, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0223, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.40990421175956726, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0304, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.359065979719162, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0204, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.29921025037765503, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0202, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.44119736552238464, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0356, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.527441143989563, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0368, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.2946699857711792, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.019, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.06720972806215286, |
| "eval_runtime": 21.7625, |
| "eval_samples_per_second": 2.068, |
| "eval_steps_per_second": 2.068, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.41129741072654724, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.024, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.3668421506881714, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0275, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.23857715725898743, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.016, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.5302643775939941, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0256, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.33516719937324524, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0123, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.4369822144508362, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0223, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.6545026898384094, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0239, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.43905889987945557, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0245, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.40151166915893555, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0346, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.5014490485191345, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0249, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.06734081357717514, |
| "eval_runtime": 21.7667, |
| "eval_samples_per_second": 2.067, |
| "eval_steps_per_second": 2.067, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.39594605565071106, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.015, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.3437756597995758, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.032, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.45787280797958374, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0341, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.3834509551525116, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0257, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.36518552899360657, |
| "learning_rate": 0.0, |
| "loss": 0.028, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.3806874734959002e+17, |
| "train_loss": 0.08482002337276935, |
| "train_runtime": 3988.4577, |
| "train_samples_per_second": 0.508, |
| "train_steps_per_second": 0.031 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 125, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.3806874734959002e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
